Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2110 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8957. Min Act: -0.1700

Data Index: 7226060 (Open Web Text)

Max Activating Token Index: 50

Text #1

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.9115. Min Act: -0.1700

Data Index: 5069055 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8787. Min Act: -0.1700

Data Index: 1701824 (Open Web Text)

Max Activating Token Index: 29

Text #3

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8412. Min Act: -0.1700

Data Index: 1939323 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8374. Min Act: -0.1700

Data Index: 1673157 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8636. Min Act: -0.1700

Data Index: 611906 (Open Web Text)

Max Activating Token Index: 34

Text #6

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8581. Min Act: -0.1700

Data Index: 7384198 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8089. Min Act: -0.1700

Data Index: 3721995 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8286. Min Act: -0.1700

Data Index: 1749274 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8064. Min Act: -0.1700

Data Index: 1017268 (Open Web Text)

Max Activating Token Index: 60

Text #10

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8082. Min Act: -0.1700

Data Index: 8206063 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8016. Min Act: -0.1700

Data Index: 713661 (Open Web Text)

Max Activating Token Index: 64

Text #12

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8060. Min Act: -0.1700

Data Index: 4141666 (Open Web Text)

Max Activating Token Index: 45

Text #13

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8231. Min Act: -0.1700

Data Index: 3269540 (Open Web Text)

Max Activating Token Index: 44

Text #14

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8160. Min Act: -0.1700

Data Index: 5588272 (Open Web Text)

Max Activating Token Index: 46

Text #15

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8107. Min Act: -0.1700

Data Index: 5582105 (Open Web Text)

Max Activating Token Index: 35

Text #16

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8266. Min Act: -0.1700

Data Index: 5535875 (Open Web Text)

Max Activating Token Index: 62

Text #17

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8007. Min Act: -0.1700

Data Index: 5370153 (Open Web Text)

Max Activating Token Index: 52

Text #18

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.7961. Min Act: -0.1700

Data Index: 2669247 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 4.9115. Min Range: -4.9115

Max Act: 4.8185. Min Act: -0.1700

Data Index: 5301465 (Open Web Text)

Max Activating Token Index: 55